ResNet101 is a convolutional neural network architecture that belongs to the ResNet (Residual Network) family.With a total of 101 layers, ResNet101 comprises multiple residual blocks, each containing convolutional layers with batch normalization and rectified linear unit (ReLU) activations. These residual blocks allow the network to effectively capture complex features at different levels of abstraction, leading to superior performance on image recognition tasks.
pip3 install onnx
pip3 install tqdm
Pretrained model: https://download.pytorch.org/models/resnet101-63fe2227.pth
Dataset: https://www.image-net.org/download.php to download the validation dataset.
python3 export.py --weight resnet101-63fe2227.pth --output resnet101.onnx
export DATASETS_DIR=/Path/to/imagenet_val/
# Accuracy
bash scripts/infer_resnet101_fp16_accuracy.sh
# Performance
bash scripts/infer_resnet101_fp16_performance.sh
# Accuracy
bash scripts/infer_resnet101_int8_accuracy.sh
# Performance
bash scripts/infer_resnet101_int8_performance.sh
Model | BatchSize | Precision | FPS | Top-1(%) | Top-5(%) |
---|---|---|---|---|---|
ResNet101 | 32 | FP16 | 2507.074 | 77.331 | 93.520 |
ResNet101 | 32 | INT8 | 5458.890 | 76.719 | 93.348 |
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。